Skip to content

ControlTower

ControlTower is the administration dashboard for the whole platform. It is where administrators configure models, providers, prompts, guardrails, and access control, deploy those settings to the running services, and monitor usage — one panel for the entire AI stack.

admin.yourdomain.com/dashboard/admin?section=models
Control Tower
A
Model Display Name Access Health Order Actions
cowork-agentagent
Cowork Agent 2 Teams 2/2 OK
llm-councilagent
LLM Council 2 Teams 1/1 OK
Databricks
sales-genieagent
Sales Genie Space Sales Team 1/1 OK
Anthropic
claude-opus-4-6
Claude Opus 4.6 All Teams 2/2 OK
OpenAI
gpt-5-5
GPT-5.5 All Teams 1/1 OK
Gemini
gemini-3-1-pro
Gemini 3.1 Pro All Teams 1/1 OK
Gemini
gemini-3-flash
Gemini 3 Flash All Teams 1/1 OK
Databricks
qwen3-next-80b
Qwen 3 Next 80B All Teams 1/1 OK
OpenAI
gpt-image-2image
GPT Image 2 All Teams 1/1 OK
Gemini
nano-banana-2image
Nano Banana 2 All Teams 1/1 OK
OpenAI
text-embedding-3-smallembedding
Text Embedding 3 Small All Teams 1/1 OK
User Email Role Teams Last Active Actions
JC
Jane Chen
jane.chen@acme.com Admin Platform 2 min ago
MR
Mike Rodriguez
mike.r@acme.com User Engineering 14 min ago
SP
Sarah Park
sarah.p@acme.com User Design 1 hr ago
AK
Alex Kim
alex.kim@acme.com Team Manager Engineering 3 hrs ago
LW
Lisa Wang
lisa.w@acme.com User Marketing 1 day ago
A
Anthropic Direct API Key
connected
Models4
Latency142ms
Uptime99.9%
O
OpenAI API Key
connected
Models3
Latency98ms
Uptime99.8%
AWS
AWS Bedrock IAM Role
connected
Models2
Latency167ms
Uptime99.7%
G
Google AI Service Account
degraded
Models1
Latency312ms
Uptime97.2%
Databricks
Databricks PAT Token
connected
Models2
Latency186ms
Uptime99.6%
E
Engineering 12 members
active
Budget$2,400/mo
Used$1,847
Models6
D
Design 5 members
active
Budget$800/mo
Used$612
Models4
M
Marketing 8 members
active
Budget$600/mo
Used$423
Models3
GroupSourceMembersTeamsActions
engineering-allAzure AD24Engineering, Platform
design-teamAzure AD8Design
marketing-allAzure AD12Marketing
Total Requests48,291+12.4%
Total Spend$3,847+8.2%
Avg Latency156ms-5.1%
Error Rate0.3%-0.1%
Usage Over Time
$300$225$150$75$0
Feb 1Feb 5Feb 10Feb 15Feb 20Feb 25Mar 1
DatetimeModelUserCachedInput TokOutput TokDurationStatus
2026-03-01 14:32:01claude-sonnet-4-6jane.chen12,4801,2048471.2s200
2026-03-01 14:31:58gpt-4.1mike.r03,8201,2040.8s200
2026-03-01 14:31:45claude-opus-4-6alex.kim8,1922,5605,1023.4s200
2026-03-01 14:31:32gemini-2.5-flashsarah.p4,0965128920.4s200
User Limits
Default New User Budget
$400
Budget Reset Period
30d
Max API Keys Per User
10
Chat App
Default Model
claude-sonnet-4-5-20250929
Key Budgets
Cowork Agent Key Budget
$100
Chat App Key Budget
$100
New API Key Budget
$50
Budget Alerts
Per-Key Alerts
enabledthreshold: 0.7
Per-User Alerts
enabledthreshold: 0.7
Team Settings
Default Team
Default Team
Budget Alerts
enabled
Health Alerts
enabled
Slack Webhook
https://hooks.slack.com/...4xK
Email Recipients
admin@acme.com, ops@acme.com
Broadcast Alert to Users
All Users Engineering Research
2026-03-05 04:00 UTC
ServerTypeToolsAccessStatusActions
Context7http2 toolsAll Usersactive
Web Search and Fetchsse2 toolsMarketing Teamactive
RuleScopeActionStatus
PII DetectionAll ModelsBlock & Alertactive
Prompt InjectionCowork AgentBlockactive
Secrets DetectionAll ModelsBlock & Alertactive

Manage system prompts, help content, and other localized strings

General
NamePreview
Budget Alert Key
Last updated: 3/2/2026
Your {platformName} API Key "{displayName}" has used {pct}% ...
Setup Instructions
Last updated: 3/2/2026
export ANTHROPIC_BASE_URL={{baseUrl}} export ANTHROPIC_A...
System Prompts
NamePreview
Default
Last updated: 3/2/2026
You are Chat App, an access interface to AI Language Models ...
Cowork Agent
Last updated: 3/2/2026
COWORK AGENT SYSTEM PROMPT (AMENDS PREVIOUS INSTRUC...
LiteLLM Config
syncedLast deployed 4 min ago
Chat App Config
pending2 changes waiting
Guardrails Config
syncedLast deployed 1 hr ago

ControlTower’s analytics view, with the admin navigation for users, teams, providers, models, guardrails, and deployment.

  • Providers and models — connect LLM providers, register models, and group them by capability.
  • System prompts — configure default and role-specific prompt content.
  • Guardrails — enable the SecondGuard checks, set their mode (including fail-closed or fail-open), and apply them globally or per team.
  • MCP tools — register Model Context Protocol tools available to chats and agents.
  • Teams, groups, and users — organize people and set their access.
  • Access control — grant model access by team, group, or user across the chat and API channels. See API Routing.
  • Localized content and general settings — including white-label branding.

ControlTower doesn’t just store configuration — it deploys rendered configs to the underlying services (the LiteLLM gateway, Chat App, guardrails, and inference) and can trigger the necessary service restarts. Changes made in the dashboard become the live configuration of the platform.

  • Usage analytics dashboards cover requests, spend, latency, and error rate, with breakdowns by user, team, and model. See Cost Management.
  • A first-party, read-only analytics interface is also exposed as an MCP tool, so usage data can be queried conversationally.
  • A Sync Jobs view shows the status of identity and membership synchronization with your upstream provider.

ControlTower presents three surfaces for different audiences:

  • Admin — full platform configuration and oversight.
  • Team supervisor — budget and usage visibility for a manager’s teams.
  • User self-service — the personal User Dashboard for keys, budgets, and logs.